Abstract

Energy consumption prediction is a popular research field in computational intelligence. However, it is difficult for general machine learning models to handle complex time series data such as building energy consumption data, and the results are often unsatisfactory. To address this difficulty, a hybrid prediction model based on modal decomposition was proposed in this paper. For data preprocessing, the variational mode decomposition (VMD) technique was used to used to decompose the original sequence into more robust subsequences. In the feature selection, the maximum relevance minimum redundancy (mRMR) algorithm was chosen to analyse the correlation between each component and the individual features while eliminating the redundancy between individual features. In the forecasting module, the long short-term memory (LSTM) neural network model was used to predict power consumption. In order to verify the performance of the proposed model, three categories of contrast methods were applied: 1) Comparing the hybrid model to a single predictive model, 2) Comparing the hybrid model with the backpropagation neural network (BPNN) to the hybrid model with the LSTM and 3) Comparing the hybrid model using mRMR and the hybrid model using mutual information maximization (MIM). The experimental results on the measured data of an office building in Qingdao show that the proposed hybrid model can improve the prediction accuracy and has better robustness compared to VMD-MIM-LSTM. In the three control groups mentioned above, the R2 value of the hybrid model improved by 10, 3 and 3%, respectively, the values of the mean absolute error (MAE) decreased by 48.9, 41.4 and 35.6%, respectively, and the root mean square error (RMSE) decreased by 54.7, 35.5 and 34.1%, respectively.

Highlights

  • Energy is critical in modern society, and energy consumption is a major issue that has long plagued humanity

  • Both the ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) algorithms are capable of handling volatile raw data, and both algorithms decompose the load into several stable components

  • To solve the modal mixing problem presented by the Empirical mode decomposition (EMD) algorithm, the VMD algorithm was used, and the value of its decomposition number K was determined by the average instantaneous frequency

Read more

Summary

INTRODUCTION

Energy is critical in modern society, and energy consumption is a major issue that has long plagued humanity. The VMD algorithm has been successfully applied in many fields, such as fault diagnosis research (Zhang et al, 2017) and forecast research (Liu et al, 2018; Niu et al, 2020) The studies of He (He et al, 2019) and Li (Li et al, 2018) have shown that the combination model based on “decompositionprediction” can achieve high prediction accuracy in heating and cooling seasons. Compared with existing studies on short-term load forecasting, the main contributions of this paper are as follows: 1) A novel deep learning-based method for predicting building electricity consumption is proposed. Note that the data decomposition and feature selection were performed on a laptop with an Intel(R) i5-7400 CPU with MATLAB 2020a installed, and the deep learning model was performed on a laptop with an Intel(R) i57400 CPU with Python 3.8 installed

METHODOLOGY
Principle of Variational Mode
Principle of Max-Relevance and Min-Redundancy
Minimum Redundancy
Prediction Model
Data Introduction
Comparison of Decomposition by EEMD and VMD
Feature Selection
Model Predictions
Model Comparison
D-1 D-2 D-3 D-4 D-5 D-6 D-8 D-23 D-24 D-12 D-25 D-7 D-9 D-10 D-22
Model Robustness
Findings
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call